Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.11189 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911106077818880 |
|---|---|
| author | Le, Chenyang Xia, Yinfeng Li, Huiyan Wang, Manhong Sun, Yutao Ma, Xingyang Qian, Yanmin |
| author_facet | Le, Chenyang Xia, Yinfeng Li, Huiyan Wang, Manhong Sun, Yutao Ma, Xingyang Qian, Yanmin |
| contents | Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large parameter sizes, making it challenging to balance inference efficiency and performance, particularly in local deployment scenarios. We propose an innovative Parasitic Dual-Scale Approach, which combines an enhanced speculative sampling method with model compression and knowledge distillation techniques. Building on the Whisper Medium model, we enhance it for multilingual speech translation into whisperM2M, and integrate our novel KVSPN module, achieving state-of-the-art (SOTA) performance across six popular languages with improved inference efficiency. KVSPN enables a 40\% speedup with no BLEU score degradation. Combined with distillation methods, it represents a 2.6$\times$ speedup over the original Whisper Medium with superior performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11189 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation Le, Chenyang Xia, Yinfeng Li, Huiyan Wang, Manhong Sun, Yutao Ma, Xingyang Qian, Yanmin Computation and Language Sound Audio and Speech Processing Recent advancements in speech-to-text translation have led to the development of multilingual models capable of handling multiple language pairs simultaneously. However, these unified models often suffer from large parameter sizes, making it challenging to balance inference efficiency and performance, particularly in local deployment scenarios. We propose an innovative Parasitic Dual-Scale Approach, which combines an enhanced speculative sampling method with model compression and knowledge distillation techniques. Building on the Whisper Medium model, we enhance it for multilingual speech translation into whisperM2M, and integrate our novel KVSPN module, achieving state-of-the-art (SOTA) performance across six popular languages with improved inference efficiency. KVSPN enables a 40\% speedup with no BLEU score degradation. Combined with distillation methods, it represents a 2.6$\times$ speedup over the original Whisper Medium with superior performance. |
| title | Novel Parasitic Dual-Scale Modeling for Efficient and Accurate Multilingual Speech Translation |
| topic | Computation and Language Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.11189 |